© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33721
    Prev
    Next
    INDEX
    Explanations

    refugee resettlement admissions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects quantitative and regulatory details in texts about refugee or immigration policy (e.g., counts, limits, or official enforcement provisions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regulation
    -0.76
     präsenti
    -0.76
    chro
    -0.75
     antidesliz
    -0.75
     बी
    -0.74
    Tomb
    -0.74
    Stealth
    -0.73
     regulated
    -0.73
     salarios
    -0.71
    Stud
    -0.70
    POSITIVE LOGITS
     reset
    1.41
     resettlement
    1.36
     Reset
    1.30
    Reset
    1.16
    reset
    1.07
     program
    1.02
    PROGRAM
    1.00
     PROGRAM
    0.94
    RESET
    0.93
    program
    0.91
    Activations Density 0.007%

    No Known Activations